CrewAI 套件的交互式用户界面。
This application provides a simplified user interface for leveraging the power of CrewAI, a cutting-edge framework for orchestrating role-playing autonomous AI agents. With this app, users can streamline the process of creating and managing AI crews without the need for coding.
V0.1 V0.2
To get started with the CrewAI Simplified App, install PostgreSQL, setup PostgreSQL user and password and follow these simple steps:
For non-developers:
Setup the project: clone or download the project then run setup_win.bat for Windows users or setup_linux_mac.sh for Linux or MacOS users.
Start the project: run start_win.bat for Windows users or start_linux_mac.sh for Linux or MacOS users. ✔Finish!
For developers:
Installation: Clone the repository and install dependencies using npm or yarn:
git clone https://github.com/Eng-Elias/CrewAI-Visualizer.git
cd CrewAI-Visualizer
npm installCreate Python Virtual Enviroment: create Python venv, activate the venv and install the requirements.
Create venv:
python -m venv venvTo activate the virtual environment on Windows:
.\venv\Scripts\activateTo activate the virtual environment on Linux or Mac:
source venv/bin/activateInstall the requirements:
pip install -r requirements.txtConfiguration: Set up your environment variables in a .env file:
Just rename .env.template to .env and set your values:
DATABASE_URL="postgresql://:@localhost:5432/crew_ai_visualizer?schema=public"
GEMINI_API_KEY=""
PYTHON_SITE_PACKAGES=""
CREW_AI_PY_FILE=""DB Migrations: Run the following commands to apply database migrations:
npx prisma generate
npx prisma migrate deployStart the Development Server: Run the following command to start the development server:
npm run devAccess the App: Once the development server is running, access the app in your browser at http://localhost:3000.
Create a New Crew: By adding agents.
Customize Agents: Fill in the information for each agent, including role, goal, backstory, tools, allow_deligation, verbose and memory.
Define Missions: Fill mission information including name, crew, verbose, process and add tasks with their details (name, description, agent, expected_output).
Execute Mission: Once your mission is set up, run it to start the execution process.
View Results: View the output of completed missions within the app.
We welcome contributions to the CrewAI Simplified App. If you'd like to contribute, please follow these steps:
This app is built using TypeScript, Prisma, GraphQL, Next.js, and node-calls-python to execute Python code from Node.js and get the result in addition to use Gemini as LLM.
This application is open-source and is released under the MIT License. See the LICENSE file for details.
Special thanks to João Moura the creator of CrewAI for providing the underlying framework for AI crew orchestration.
If you find CrewAI Visualizer helpful and would like to support its development, consider buying me a coffee! Your support will allow me to dedicate more time to enhancing and adding new features to CrewAI Visualizer.
暂无开放 Issues,或尚未同步最近议题。